This project implements a multi-camera tracking system that combines YOLO object detection, epipolar geometry-based matching, triangulation and 3D tracking to provide 3D object localization and ...

Mesh-adsorbed Gaussian Splatting (MaGS) is a novel framework for reconstructing and simulating dynamic 3D objects. It combines the rendering flexibility of 3D Gaussians with the spatial coherence of ...

Abstract: Inferring affordance for 3D articulated objects is a challenging and practical problem. It is a primary problem for applying robots to real-world scenarios. The exploration can be summarized ...

Abstract: Recent progress on multi-modal 3D object detection has featured BEV (Bird-Eye-View) based fusion, which effectively unifies both LiDAR point clouds and camera images in a shared BEV space.